© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 14301
    Prev
    Next
    INDEX
    Explanations

    themes of progress and transformation in technology and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoryboardSegue
    -0.46
     Italijanski
    -0.46
    ArrowToggle
    -0.45
    ParallelGroup
    -0.44
     SwitchCompat
    -0.42
    OrBuilder
    -0.41
     particulières
    -0.41
     justement
    -0.41
     propOrder
    -0.40
     Comprometido
    -0.39
    POSITIVE LOGITS
     commonplace
    1.38
     common
    1.05
     routine
    1.03
     norm
    1.01
     prevalent
    0.99
     standard
    0.96
     normal
    0.95
     ubiquitous
    0.92
     accepted
    0.89
    common
    0.88
    Activations Density 0.704%

    No Known Activations